检索结果-内蒙古大学图书馆

International Conference on Data engineering

作者： Xiaokun Fang Feng Zhang Junxiang Nong Mingxing Zhang Puyun Hu Yunpeng Chai Xiaoyong Du Key Laboratory of Data Engineering and Knowledge Engineering (MOE) and School of Information Renmin University of China Department of Computer Science and Engineering Tsinghua University

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Text analytics directly on compression (TADOC) is a promising technology designed for handling big data analytics. However, a substantial amount of DRAM is required for high performance, which limits its usage in many important scenarios where the capacity of DRAM is limited, such as memory-constrained systems. Non-volatile memory (NVM) is a novel storage technology that combines the advantage of reading per-formance and byte addressability of DRAM with the durability of traditional storage devices like SSD and HDD. Unfortunately, no research demonstrates how to use NVM to reduce DRAM utilization in compressed data analytics. In this paper, we propose N-TADOC, which substitutes DRAM with NVM while maintaining TADOC's analytics performance and space savings. Utilizing an NVM block device to reduce DRAM utilization presents two challenges, including poor data locality in traversing datasets and auxiliary data structure reconstruction on NVM. We develop novel designs to solve these challenges, including a pruning method with NVM pool management, bottom-up upper bound estimation, correspondent data structures, and persistence strategy at different levels of cost. Experimental results show that on four real-world datasets, N-TADOC achieves 2.04× performance speedup compared to the processing directly on the uncompressed data and 70.7% DRAM space saving compared to the original TADOC.

关键词： Performance evaluation Upper bound Data analysis Costs Nonvolatile memory Random access memory Estimation

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on Advancements in Text Mining and Natural Language Processing

A Comprehensive Study on Advancements in Text Mining and Nat...

引用

Emerging Research in Computational science (ICERCS), International Conference on

作者： Sarthak Mahire U K Balaji Saravanan Murali M Prabakaran N School of Computer Science and Engineering Vellore Institute of Technology Vellore India Department of Computer Science and Engineering Knowledge Institute of Technology Salem India Department of Information Technology Sona College of Technology Salem India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534974

Text mining and Natural Language Processing (NLP) have witnessed significant advancements in recent years, driven by the increasing availability of unstructured data and the development of sophisticated machine learning models. This review explores the evolution of text mining and NLP, highlighting the transition from rule-based systems to modern deep learning approaches. This paper reviews various techniques and its impact across various domains. Challenges such as data bias and model interpretability still remain. The paper also discusses future directions, emphasizing the need for fair, interpretable and sustainable NLP systems. This paper aims to provide insights into the current state of text mining and NLP, the challenges faced and potential pathways for future research.

关键词： Text mining Training Technological innovation Reviews Scientific computing Focusing Medical services Natural language processing Data models Multilingual

来源：评论

学校读者我要写书评

暂无评论

Enabling Generalized Zero-Shot Vulnerability Classification

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Hu, Jinghao Guo, Jinsong Luo, Chen Hu, Yang Lanzinger, Matthias Li, Zhanshan Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Software Changchun130012 China University College London Department of Computer Science United Kingdom Amazon United States United Kingdom University of Oxford Department of Computer Science United Kingdom Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Changchun130012 China

Regarding computer security, the growth of code vulnerability types presents a persistent challenge. These vulnerabilities, which may cause severe consequences, necessitate precise classification for effective mitigation. However, the rapid emergence of new vulnerability types complicates the classification process. Traditional methodologies, which often involve human expertise and the manual labeling or generation of example instances, are not only resource-intensive but also struggle to adapt to the dynamic nature of these vulnerabilities. This paper introduces VulnSense, an innovative method that harnesses the capabilities of Generalized Zero-Shot Learning (GZSL) to address the vulnerability classification problem. VulnSense learns about unseen vulnerability classes from the descriptions of these unseen classes, while not requiring to see any instances of these unseen classes. Specifically, VulnSense learns from three main resources: (1) seen classes with labeled code instances;(2) descriptions of these seen classes;and (3) descriptions of "unseen"classes which have no labeled instances. Our experiments underscore VulnSense's superiority over existing GZSL methods in classifying instances of unseen classes. Concurrently, it maintains a performance parity with traditional labeled-example based learning methods in classifying instances of seen vulnerabilities. VulnSense demonstrates the potential of using GZSL for vulnerability classification, while also highlighting challenges that inspire future work. © 2004-2012 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Affine Non-local Means Image Denoising 11th

Affine Non-local Means Image Denoising

引用

11th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2023

作者： Anand, Rohit Koti, Valli Madhavi Sharma, Mamta Ajagekar, Supriya Sanjay Dhabliya, Dharmesh Gupta, Ankur New Delhi110020 India Department Computer Science GIET Degree College NH-16 Chaitanya Knowledge City Andhra Pradesh Rajahmundry533294 India Department of CSE and CSA Arni University Himachal Pradesh Kangra India Department of Engineering and Technology Bharati Vidyapeeth Deemed University Navi Mumbai India Department of Information Technology Vishwakarma Institute of Information Technology Maharashtra Pune India Department of Computer Science and Engineering Vaish College of Engineering Haryana Rohtak India

ISBN: (纸本)9789819967018

In subsequent activities like image identification and medical diagnosis, digital pictures are frequently damaged by noise during capture and transmission. When damaged photos must be utilized, several denoising techniques have been suggested to increase the accuracy of these jobs. However, the majority of these techniques either call for making assumptions on the statistical characteristics of the corrupting noise or are specifically created solely for a certain kind of noise. The performance of traditional image denoising algorithms that use lone noisy images and general image databases will soon be reached. In this article, we suggest denoising images with specific external image databases. Denoising is formulated as an optimum filter design issue, and we use the focused databases to (1) find the fundamental properties of the ideal filter using group sparsity, and (2) find spectral coefficients of the optimal filter using localized priors. Research exhibits better denoising outcomes than current methods for a range of circumstances, adding photos and text, multitier pictures, as well as face images. In contrast to employing a general database, we present an adaptive picture denoising approach in this study. In this context, a focused database is one that only contains photos pertinent to the noisy image. Targeted external databases might be acquired in several real-world settings, including text pictures, human faces, and photos taken by multi-view camera systems, as will be demonstrated in subsequent sections of this work. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of IoT Data Using Machine Learning Algorithms 15th

A Comparative Analysis of IoT Data Using Machine Learning Al...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Nagashree, B.A. Satheesh Kumar, S. Muthukumaran, V. Munrathnam, Meram Angeline Kavitha, M. Department of Computer Science and Applications School of CSA REVA University Bangalore India Department of Computer Science School of Applied Sciences REVA University Bangalore India Department of Mathematics College of Engineering and Technology SRM Institute of Science and Technology Chennai India Department of Mathematics Rajiv Gandhi University of Knowledge Technologies R.K. Valley Kadapa District Andhra Pradesh Idupulapaya516330 India Department of Mathematics Voorhees College Vellore632001 India

ISBN: (纸本)9783031889912

IoT (Internet of Things) is revolutionizing the commercial environment by acquiring vast amounts of data from various sources. However, processing and analyzing this data is challenging due to the large volume of IoT devices. AI-powered IoT creates intelligent machines that mimic human intelligence, aiding decision-making with minimal human input. Both individuals and professionals’ benefit from this combination, as IoT is concerned with communicating online, but AI allows machines to learn from data and experience. This study demonstrates the analysis of IoT data using machine learning algorithms and compares the accuracy of various machine learning algorithms used. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Navigating the Generative AI Project Ecosystem with a Focus on Addressing Data Architecture Complexities and Strategic Model Selection for Optimal Outcomes

Navigating the Generative AI Project Ecosystem with a Focus ...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Gupta, Priyanka Kumari, I. Vasantha Rajalakshmi, B. Nijhawan, Ginni Praveen Mazaal, Zahraa Sahib Institute of Aeronautical Engineering Hyderabad Dundigal India Siddhartha Institute of Technology and Sciences Medchal Malkajgiri District Hyderabad Telangana India New Horizon College of Engineering Department of Computer Science Bangalore India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India National University of Science and Technology Collage of Dentist Dhi Qar64001 Iraq

ISBN: (纸本)9798350373783

This article discusses the Generative Artificial Intelligence (AI) project's complex ecology and how to pick the optimal models and data design. Creative AI in many commercial and academic fields presents new issues and opportunities. Knowing your way around generative AI projects is crucial. Choose models carefully since data design is hard to grasp. This research provides comprehensive guidance on how to address these areas and ensure project success. Data architecture study is the first step towards generative artificial intelligence since it identifies common issues and viable solutions. Next, to determine which generative models - in terms of complexity, scalability, and ethics - are best suited for a range of tasks, we must evaluate and compare many of them. Researchers were able to validate these findings using case studies and expert interviews. The results suggest that an ordered data infrastructure is required for creative AI. This study indicated the need to boost generational artificial intelligence programs by making practitioners and researchers more aware of the challenges. The study argues that further research and development are necessary to keep up with the fast progress of creative artificial intelligence. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Information Extraction and Analysis on Certificates and Medical Receipts

Information Extraction and Analysis on Certificates and Medi...

引用

2022 IEEE International Conference on Consumer Electronics, ICCE 2022

作者： Hong, Tzung-Pei Chen, Wei-Chou Wu, Chih-Hung Xiao, Bo-Wen Chiang, Bing-Yang Shen, Zhi-Xun National University of Kaohsiung Department of Computer Science and Information Engineering Kaohsiung Taiwan CoreTech Knowledge Inc. Hsinchu Taiwan National University of Kaohsiung Department of Electrical Engineering Kaohsiung Taiwan

ISBN: (纸本)9781665441544

Document digitalization has become a trend in recent years. It provides fast analysis and search because the information in the documents can be easily managed. However, in real applications, while digitalization is in progress, lots of information has not yet been digitalized and only stored on papers. A common demand of analyzing a large amount of documents would be a time-consuming mission because they need massive human labor. Nowadays, some computer vision algorithms have emerged and they can be applied in such a scenario. In this paper, we propose an automatic information extraction and analysis system for mandarin documents. It consists of three main steps. Firstly, the text regions in documents under natural scenes are detected. Secondly, these text regions are recognized and converted into digital forms. Finally, heuristic rules are designed and integrated into the system to improve the recognition accuracy. The proposed system is expected to eliminate the time-consuming problem of document information extraction. © 2022 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Sign Language Video Generation Using Deep Networks

A Novel Approach for Sign Language Video Generation Using De...

引用

Data science and Network Security (ICDSNS), International Conference on

作者： Sachin Kumar Deepa B Kavitha T Tamilselvi M Sathiyapriya V Natarajan B Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Department of Electroncis and Communication Engineering SRMIST Ramapuram Campus Ramapuram India Department of Computer Science and Engineering MA.M College of Engineering and Technology Trichy India Department of Computer Science and Engineering Roever Engineering College Perambalur India Department of Computer Science and Engineering Knowledge Institute of Technology Salem India School of Computer Science and Engineering Vellore Institue of Technology Chennai Campus Chennai India

ISBN: (数字)9798350373110

ISBN: (纸本)9798350373127

Sign language enhances the communication capabilities of the deaf-mute community, allowing for a deeper understanding of their needs and emotions. These languages are highly structured and visual, using gestures and various upper body movements such as those of the hands, face, eyes, and gaze. Researchers face numerous challenges in recognizing and translating the diverse variations in sign movements, which requires specialized expertise in computer vision and artificial intelligence. Sign language recognition and translation research has garnered global attention. This research work introduces a novel methodology for generating sign gesture videos from text inputs by integrating various intelligent techniques. The proposed model employs an enhanced generative adversarial network (GAN) to create sign videos from input sentences. Experiments with the proposed VideoGAN model using diverse sign language datasets from multiple countries have demonstrated its effectiveness. The research outcomes highlight its contribution to high-quality video production, with improved evaluation metrics underscoring the model's superior performance.

关键词： Measurement Training Sign language Visualization Face recognition Refining Production Assistive technologies Generative adversarial networks Videos

来源：评论

学校读者我要写书评

暂无评论

Dual-level Mixup for Graph Few-shot Learning with Fewer Tasks

arXiv

引用

arXiv 2025年

作者： Liu, Yonghao Li, Mengyu Giunchiglia, Fausto Huang, Lan Li, Ximing Feng, Xiaoyue Guan, Renchu College of Computer Science and Technology Jilin University Changchun China Department of Information Engineering and Computer Science University of Trento Trento Italy Key Laboratory of Symbolic Computation and Knowledge Engineering The Ministry of Education China

Graph neural networks have been demonstrated as a powerful paradigm for effectively learning graph-structured data on the web and mining content from it. Current leading graph models require a large number of labeled samples for training, which unavoidably leads to overfitting in few-shot scenarios. Recent research has sought to alleviate this issue by simultaneously leveraging graph learning and meta-learning paradigms. However, these graph meta-learning models assume the availability of numerous meta-training tasks to learn transferable meta-knowledge. Such assumption may not be feasible in the real world due to the difficulty of constructing tasks and the substantial costs involved. Therefore, we propose a SiMple yet effectIve approach for graph few-shot Learning with fEwer tasks, named SMILE. We introduce a dual-level mixup strategy, encompassing both within-task and across-task mixup, to simultaneously enrich the available nodes and tasks in meta-learning. Moreover, we explicitly leverage the prior information provided by the node degrees in the graph to encode expressive node representations. Theoretically, we demonstrate that SMILE can enhance the model generalization ability. Empirically, SMILE consistently outperforms other competitive models by a large margin across all evaluated datasets with in-domain and cross-domain settings. Our anonymous code can be found here. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Output Constrained Adaptive Controller Design for Nonlinear Saturation Systems

引用

IEEE/CAA Journal of Automatica Sinica 2021年第2期8卷 441-454页

作者： Yongliang Yang Zhijie Liu Qing Li Donald C.Wunsch the Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical EngineeringUniversity of Science and Technology BeijingBeijing 100083China the Department of Electrical and Computer Engineering Missouri University of Science and TechnologyRollaMO 65409 USA

This paper considers the adaptive neuro-fuzzy control scheme to solve the output tracking problem for a class of strict-feedback nonlinear *** asymmetric output constraints and input saturation are *** asymmetric barrier Lyapunov function with time-varying prescribed performance is presented to tackle the output-tracking error constraints.A high-gain observer is employed to relax the requirement of the Lipschitz continuity about the nonlinear *** avoid the"explosion of complexity",the dynamic surface control(DSC)technique is employed to filter the virtual control signal of each *** deal with the actuator saturation,an additional auxiliary dynamical system is *** is theoretically investigated that the parameter estimation and output tracking error are semi-global uniformly ultimately *** simulation examples are conducted to verify the presented adaptive fuzzy controller design.

关键词： Asymmetric barrier Lyapunov function input saturation Nussbaum function time-varying prescribed performance

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：